JP2022051991A - Information processing device, information processing method, and program - Google Patents

Abstract

To estimate, when it is assumed that one of a plurality of parameters expressing an acquired operation state has been changed or is changing, a value of another parameter which changes in linkage with the operation.SOLUTION: A parameter acquisition unit 211 acquires, as indexes indicating an action state of a subject, a value of a first parameter and a value of a second parameter which is an index different from the first parameter and has correlation with the first parameter. A parameter estimation unit 213 estimates a value of the second parameter corresponding to another first parameter according to a model in which a third parameter generated on the basis of a combination of a value of a third parameter being the same type as the first parameter and indicating an action state of each of a plurality of subjects stored in an action state storage DB 222 and a value of a fourth parameter being the same type as the second parameter is input and the fourth parameter is output.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing apparatus, an information processing method and a program.

There is known a technique for measuring various indexes (parameters) indicating a user's motion state by using a wearable device or a motion sensor worn on the user's body. Patent Document 1 discloses an invention that displays an animation representing a user's movement based on various indexes representing the acquired motion state. In the invention described in Patent Document 1, when the value of the index is manually changed by the user, the animation can be changed according to the changed value.

Japanese Unexamined Patent Publication No. 2018-026149

Among the parameters representing the exercise state, it is known that when the values of other parameters change, the values change in conjunction with the changes. In the invention described in Patent Document 1, even if the user manually changes the value of the parameter, the values of other parameters that are presumed to change in conjunction with the change do not change, so that the animation after the change is unnatural. There is a risk of making a lot of movement.

The present invention has been made in view of the above circumstances, and when one of a plurality of parameters representing the acquired exercise state changes or is assumed to change, the other changes in conjunction with the change. It is an object of the present invention to provide an information processing apparatus, an information processing method and a program capable of estimating a parameter value.

In order to achieve the above object, the information processing apparatus according to the present invention is
An acquisition means for acquiring the value of the first parameter and the value of the second parameter, which is an index different from the first parameter and having a correlation, as an index indicating the exercise state of a certain subject.
A parameter acquisition means for acquiring another first parameter, which is the first parameter having a value different from the value of the first parameter acquired by the acquisition means, and a parameter acquisition means.
Based on the set of the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter, which represent the motion state of each of the plurality of subjects of the same type as the certain subject. According to the model generated by inputting the value of the third parameter and outputting the value of the fourth parameter, the first reference value as the second parameter is derived based on the first parameter acquired by the acquisition means. The first derivation means to be
A second derivation means for deriving a second reference value as the second parameter based on the other first parameter acquired by the parameter acquisition means according to the model.
A parameter estimation means that estimates the value of the second parameter corresponding to the other first parameter based on the value of the second parameter, the first reference value, and the second reference value acquired by the acquisition means. When,
To prepare for.

According to the present invention, when one of a plurality of parameters representing the acquired exercise state changes or is assumed to change, it is possible to estimate the values of other parameters that change in conjunction with the change. It becomes.

It is a figure which shows the configuration example of the animation generation system which concerns on embodiment. It is a figure which shows the example of the information stored in the exercise state memory DB. It is a flowchart of the parameter acquisition process which concerns on embodiment. It is a flowchart of the animation generation processing which concerns on embodiment. It is a figure which shows the example of the screen which displays the generated animation. It is a flowchart of the parameter estimation process which concerns on embodiment. It is a figure which shows the distribution of the set of the acquired velocity and the pitch value, and the model generated from this distribution. It is a figure for demonstrating an example of estimating a parameter. It is a figure which shows the distribution of the set of the acquired velocity and the vertical motion value, and the model generated from this distribution. It is a figure which shows the distribution of the set of the acquired pitch and the vertical movement value, and the model generated from this distribution.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the figure are designated by the same reference numerals.

(Embodiment)
The animation generation system 1000 according to the embodiment of the present invention is a system that generates an animation expressing the movement (form) of a user (subject) who is performing a moving motion such as running. As shown in FIG. 1, the animation generation system 1000 includes a data transmission device 100 and an animation generation device 200. In reality, a plurality of data transmission devices 100 are provided for each subject.

The data transmission device 100 is, for example, a small wearable device worn near the waist along the trunk of the subject. As shown in FIG. 1, the data transmission device 100 includes a control unit 110, a storage unit 120, a communication unit 131, an input unit 132, an output unit 133, and a sensor unit 134. The control unit 110, the storage unit 120, the communication unit 131, the input unit 132, the output unit 133, and the sensor unit 134 are connected to each other via the bus line BL. The data transmission device 100 transmits data indicating the movement of the subject detected by the sensor unit 134 to the animation generation device 200 via the communication unit 131.

The control unit 110 includes a CPU (Central Processing Unit) and the like. The control unit 110 functions as an exercise data transmission unit 111, which will be described later, by executing a program stored in the storage unit 120.

The storage unit 120 includes a ROM (Read Only Memory), a RAM (Random Access Memory), a flash memory, and the like, and stores a program executed by the CPU of the control unit 110 and necessary data. The data to be stored even after the power of the data transmission device 100 is turned off is stored in a non-volatile memory such as a flash memory.

The communication unit 131 includes a wireless communication module and an antenna, and wirelessly communicates data with the animation generator 200. Further, the communication unit 131 is not limited to the wireless method in the data communication with the animation generation device 200, and may perform the data communication by using a wired interface such as USB (Universal Serial Bus).

The input unit 132 includes a push button switch or the like, and receives input instructions from the subject such as "measurement start" and "data transmission".

The output unit 133 includes an LED (Light Emitting Diode), a liquid crystal display panel, an organic EL (Electro-Luminence) display panel, and the like, and displays an operating state (power ON, measurement, data transmission, etc.) of the data transmission device 100. do. Further, the output unit 133 includes a voice output device such as a speaker, and outputs information indicating an operating state of the data transmission device 100 as voice information.

The sensor unit 134 includes an acceleration sensor, a gyro (angular velocity) sensor, a GPS (Global Positioning System) receiver, and the like, and detects the movement of the subject and the current position of the subject on which the data transmission device 100 is attached. The sensor unit 134 transmits the acceleration data detected by the acceleration sensor, the angular velocity data detected by the gyro sensor, the time data and the position data received by the GPS receiver, and the like to the control unit 110. Since these data transmitted by the sensor unit 134 to the control unit 110 are data for expressing the motion state of the subject to which the data transmission device 100 is attached, they are collectively referred to as "exercise data" hereafter. The data transmission device 100 (sensor unit 134) may be attached to a portion other than the waist of the subject (for example, a wrist or ankle). Further, the data transmission device 100 may include a plurality of sensor units 134, such as a sensor unit 134 attached to the waist of the subject, a sensor unit 134 attached to the wrist, and a sensor unit 134 attached to the ankle. good.

Next, the function of the control unit 110 will be described. The control unit 110 functions as an exercise data transmission unit 111 by executing a program stored in the storage unit 120.

The motion data transmission unit 111 transmits the motion data (acceleration data, angular velocity data, time data, position data, etc. indicating the motion of the subject) detected by the sensor unit 134 to the animation generation device 200 via the communication unit 131. Send. The motion data transmission unit 111 may also transmit the movement distance data calculated from the position data, the velocity data calculated from the time data and the position data, the acceleration data, and the like to the animation generation device 200 as motion data. ..

Next, the animation generation device 200 will be described. The animation generation device 200 is, for example, a terminal device such as a PC (Personal Computer), a smartphone, or a tablet. As shown in FIG. 1, the animation generation device 200 includes a control unit 210, a storage unit 220, a communication unit 231, an input unit 232, and an output unit 233. The control unit 210, the storage unit 220, the communication unit 231 and the input unit 232 and the output unit 233 are connected to each other via the bus line BL. The animation generation device 200 calculates the values of a plurality of different types of parameters as an index representing the running motion state from the motion data transmitted by the data transmission device 100, and generates an animation expressing the running motion of the subject. , Present to the subject.

The control unit 210 includes a CPU and the like. The control unit 210 functions as each unit (parameter acquisition unit 211, animation generation unit 212, parameter estimation unit 213) described later by executing the program stored in the storage unit 220.

The storage unit 220 includes a ROM, a RAM, a flash memory, and the like, and stores a program executed by the CPU of the control unit 210 and necessary data. The data to be stored even after the power of the animation generation device 200 is turned off is stored in a non-volatile memory such as a flash memory. Further, the storage unit 220 stores the user DB (DataBase) 221 and the exercise state storage DB 222.

The user DB 221 is a database in which information about a subject of the data transmission device 100 is registered. Specifically, the user DB 221 contains a user ID, name, gender, physique (height, weight, etc.), running history, best time, etc. that uniquely identify the subject for each subject of the data transmission device 100. The information to be shown is stored.

The exercise state storage DB 222 is a database in which a plurality of parameters representing the running exercise states of the subject measured so far are stored. Specifically, as shown in FIG. 2, the exercise state storage DB 222 contains the user ID of the subject and the speed and pitch (per unit time) of the locomotion of the subject as parameters representing the exercise state of the subject. A plurality of exercise parameter information associated with each value of step count) and vertical movement, and information indicating the measurement date and time when these parameters were measured is stored. It is empirically known that the values of velocity, pitch, and vertical movement, which are parameters representing the user's motion state, are correlated with each other and change in conjunction with each other as the subject's motion state changes. Has been done. For example, when the velocity of the subject changes, the pitch and the vertical movement also change in conjunction with each other.

The communication unit 231 includes a wireless communication module and an antenna, and wirelessly communicates data with the data transmission device 100. Further, the communication unit 231 is not limited to the wireless method in the data communication with the data transmission device 100, and may perform the data communication by using a wired interface such as USB.

The input unit 232 includes a switch, a touch panel, a keyboard, a mouse, and the like, and receives input instructions from the subject such as "animation generation" and "parameter change".

The output unit 233 includes a liquid crystal display panel, an organic EL display panel, and the like, and displays, for example, an animation generated by an animation generation process described later, or a screen for changing parameters. Further, the output unit 233 may include an audio output device such as a speaker, and may output audio or the like related to the animation generated by the animation generation process.

Next, the function of the control unit 210 will be described. The control unit 210 functions as a parameter acquisition unit 211, an animation generation unit 212, and a parameter estimation unit 213 by executing a program stored in the storage unit 220.

The parameter acquisition unit 211 obtains motion data (acceleration data, angular velocity data, time data, position data, travel distance data, velocity data, etc.) indicating the movement of the subject acquired from the data transmission device 100 via the communication unit 231. get. Then, the parameter acquisition unit calculates a plurality of correlated parameters (speed, pitch, vertical movement) representing the running exercise state of the subject from the income data, and registers them in the exercise state storage DB 222. The parameter acquisition unit 211 functions as an acquisition means.

As a method for the parameter acquisition unit 211 to calculate each parameter from motion data, a known method described in Japanese Patent No. 66448439, Japanese Patent Application Laid-Open No. 2019-216798, or the like can be adopted.

For example, the parameter acquisition unit 211 can calculate the velocity from the time change of the position data indicated by the motion data. Further, the parameter acquisition unit 211 can obtain the cycle (running cycle) of the waveform of the vertical component of the acceleration indicated by the motion data, and can calculate the pitch from the running cycle. Further, the parameter acquisition unit 211 integrates the vertical component of the acceleration indicated by the motion data, so that the position from the landing of one foot to the landing of the other foot (the subject to which the data transmission device 100 is attached) The vertical movement can be calculated as the difference between the highest point and the lowest point of the waist position).

The animation generation unit 212 generates an animation representing the movement of the corresponding subject based on each value of the plurality of parameters designated as the target of the animation. The animation generation unit 212 functions as an animation generation means.

When the value of one of the plurality of parameters designated as the target of animation is changed, the parameter estimation unit 213 is a value between the plurality of parameters from the plurality of motion parameter information stored in the motion state storage DB 222. Generate a model that defines the relationship between, and estimate the values of parameters that are considered to change in conjunction with each other. The parameter estimation unit 213 functions as a parameter acquisition means, a first derivation means, a second derivation means, and a parameter estimation means.

Next, the processing executed by the animation generation device 200 will be described. First, the parameter acquisition process executed by the animation generation device 200 will be described. The subject of the data transmission device 100 is equipped with the data transmission device 100, inputs an instruction of "start of exercise data measurement" via the input unit 132, and then performs, for example, running or walking as an exercise. As a result, the sensor unit 134 of the data transmission device 100 continues to measure the exercise data of the subject who is running or walking at predetermined time intervals (for example, every second). After that, the subject who has finished running is instructed to "end the exercise data measurement" via the input unit 132. As a result, the motion data transmission unit 111 transmits the motion data that has been continuously measured to the animation generation device 200 together with the user ID of the subject. Upon receiving the motion data from the data transmission device 100, the parameter acquisition unit 211 of the animation generation device 200 executes the parameter acquisition process shown in FIG.

First, the parameter acquisition unit 211 divides the received exercise data into predetermined measurement times (for example, 5 minutes) (step S101). For example, if the predetermined measurement time is 5 minutes and the received exercise data is the exercise data for 1 hour, the exercise data is divided into 12 pieces in step S101. The parameter acquisition unit 211 may determine the timing at which the speed changes by a certain threshold value or more from the transition of the speed of the subject indicated by the received movement data, and may divide the movement data at that timing.

Subsequently, the parameter acquisition unit 211 calculates the value of each parameter (speed, pitch, vertical movement, etc.) indicating the movement state of the subject from the movement data for each movement data divided in step S101 (step S102). ..

Subsequently, the parameter acquisition unit 211 registers the exercise parameter information including each calculated parameter in the exercise state storage DB 222 (step S103). For example, if the exercise data is divided into 12 in step S101, the 12 exercise parameter information is registered in the exercise state storage DB 222. The user ID included in the exercise parameter information is set to the user ID received together with the exercise data. This completes the parameter acquisition process.

In the parameter acquisition process described above, the animation generation device 200 calculated each parameter from the motion data received from the data transmission device 100, but the data transmission device 100 calculated each parameter from the motion data acquired by the sensor unit 134. Then, it may be transmitted to the animation generation device 200.

Next, the animation generation process executed by the animation generation device 200 will be described. Prior to the animation generation process, the above-mentioned parameter acquisition process is executed for a plurality of subjects, and a sufficient number (for example, 100 or more) of motion parameter information is stored in the motion state storage DB 222. And. When the subject inputs the instruction of "animation generation" via the input unit 232 of the animation generation device 200, the animation generation unit 212 starts the animation generation process shown in FIG.

First, the animation generation unit 212 receives the values of each parameter (speed, pitch, vertical movement) to be animated from the subject (step S201). For example, the animation generation unit 212 receives the selection of the exercise parameter information stored in the exercise state storage DB 222 from the subject via the input unit 232, and animates the value of each parameter included in the selected exercise parameter information. Accept as the target of. The animation generation device 200 may accept the value of each parameter directly input by the subject via the input unit 232.

Subsequently, the animation generation unit 212 creates an animation representing the running motion state of the subject based on the values of the received parameters, and displays it on the output unit 233 as shown in FIG. 5 (step S202). On this screen, the generated animation is displayed on the right side, and the value of each parameter (speed, pitch, vertical movement) that is the source of this animation and the slide bar for changing the value of each parameter are displayed on the left side. Is displayed.

Returning to FIG. 4, when the subject wants to change one of the parameters that are the basis of the displayed animation, the amount of the subject wants to change the slide bar next to the parameter to be changed via the input unit 232. Move left and right to the position corresponding to. Upon receiving the operation of changing the parameter (step S203; Yes), the parameter estimation unit 213 executes a parameter estimation process for estimating the value of another parameter that changes in conjunction with the changed parameter (step S204).

The parameter estimation process will be described in detail with reference to FIG. In the following description, the parameter whose value has changed due to the operation of the subject is defined as the first parameter, and the other parameter whose value is estimated to change in association with this is defined as the second parameter. For example, when the subject performs an operation of changing the speed from the screen shown in FIG. 5 via the input unit 232, the speed is the first parameter and the pitch or the vertical movement is the second parameter.

When the parameter estimation process is started, the parameter estimation unit 213 acquires the value of the first parameter and the value of the second parameter before being changed by the operation of the subject (step S301).

Subsequently, the parameter estimation unit 213 uses the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter indicated by each of the plurality of movement parameter information stored in the movement state storage DB 222. Based on all the pairs of and, a model is created in which the value of the third parameter is input and the value of the fourth parameter is output (step S302). This model corresponds to, for example, a function (regression equation) of a regression curve created by the least squares method. In addition, the parameter estimation unit 213 is a model of the value of the fourth parameter including a set of a certain ratio or more (for example, 60% or more) among all the sets of the value of the third parameter and the value of the fourth parameter. Further reliability intervals indicating the range may be obtained.

For example, FIG. 7 shows the distribution of a set of a velocity as a third parameter and a pitch as a fourth parameter shown by each of the plurality of motion parameter information stored in the motion state storage DB 222. In this figure, one "*" corresponds to a set of velocity and pitch included in one motion parameter information. In step S302, a model is created from this distribution in which the velocity is input and the pitch is output by the method of least squares. The solid curve F in this figure is a regression curve corresponding to the model created from this distribution. Further, the curves A and B of the two alternate long and short dash lines indicate the upper limit and the lower limit of the reliability interval, respectively. 60% of the set of velocity and pitch indicated by "*" is included in the range between the curves A and B of the alternate long and short dash line. The curves A and B that define the reliability interval are obtained by a known method based on the relationship between the curve F and the distribution of the set of velocity and pitch.

Returning to FIG. 6, the parameter estimation unit 213 inputs the value of the first parameter acquired in step S301 before the value is changed into the created model, and is the value of the second parameter. 1 Derivation of a reference value (step S303).

Subsequently, the parameter estimation unit 213 inputs the value of the first parameter after the value is changed by the operation of the subject into the created model, and derives the second reference value which is the value of the second parameter. (Step S304).

Subsequently, the parameter estimation unit 213 interlocks with the changed first parameter based on the value of the second parameter before the change, the first reference value, and the second reference value acquired in step S301. Estimate the value of the second parameter that changes (step S305). This completes the parameter estimation process.

Here, the process of step S305 will be described with an example. Here, it is assumed that the first parameter and the third parameter are velocities, the second parameter and the fourth parameter are pitches, and the model is generated as shown by the curve F shown in FIG. Then, consider a case where only the velocity value is changed to V2 by the operation of the subject from the state where the velocity value is V1 and the pitch value is P1. In this case, the parameter estimation unit 213 estimates that the pitch value changes along the curve F. That is, the parameter estimation unit 213 estimates the pitch value P2, which is the second parameter that changes in conjunction with the following equation.
P2 = S2 + K * (P1-S1)

As shown in FIG. 8, P1 in this equation indicates a pitch value corresponding to the velocity V1 before the velocity is changed to V2, S1 indicates a first reference value, and S2 indicates a second reference value. Further, K in this equation is a coefficient arbitrarily set in the range of 0 to 1, and K is usually set to 1.0. When it is desired to bring P2, which is an estimated value of the second parameter after the change, closer to the second reference value S2, K is set to a value close to 0.0.

When the reliability interval is also calculated as a model, the parameter estimation unit 213 estimates P2 in consideration of the ratio of the lengths of the reliability interval (T2 / T1) as shown in the following equation. You may.
P2 = S2 + K * (P1-S1) * T2 / T1

As shown in FIG. 8, T1 in this equation represents the length of the reliability interval at the velocity V1 before the change. T2 represents the length of the reliability interval at the velocity V2 after the change. For example, as a function of velocity v, the equation of the curve A is expressed as a (v), and the equation of the curve B is expressed as b (v). In this case, T1 and T2 may be calculated by the following formulas.
T1 = a (V1) -b (V1)
T2 = a (V2) -b (V2)

Here, an example of estimating the pitch, which is the second parameter, when the velocity, which is the first parameter, is changed, is shown, but a set of other parameters whose values have a correlation is the first parameter. It may be used as the second parameter. For example, when the pitch which is the first parameter is changed by reversing the first parameter and the second parameter, the velocity which is the second parameter may be estimated by the same method.

For example, there is also a correlation between velocity and vertical movement, and as shown in FIG. 9, from the distribution of the pair of velocity and vertical movement, the regression curve F'and the reliability interval (curve A'and curve B) are used as a model. If the interval between') can be obtained, this model can be used to similarly estimate the vertical movement, which is the second parameter, when the velocity, which is the first parameter, is changed. Alternatively, the speed, which is the second parameter, may be estimated in the same manner when the vertical movement, which is the first parameter, is changed by reversing the first parameter and the second parameter.

For example, there is also a correlation between pitch and vertical movement, and as shown in FIG. 10, from the distribution of the pair of pitch and vertical movement, a regression curve F'' and a reliability interval (curve A'' are used as models. If the interval between the curves B'' can be obtained, this model can be used to similarly estimate the vertical movement, which is the second parameter, when the pitch, which is the first parameter, is changed. be. Alternatively, the pitch, which is the second parameter, may be estimated in the same manner when the vertical movement, which is the first parameter, is changed by reversing the first parameter and the second parameter.

Returning to FIG. 4, when the parameter estimation process (step S204) is completed, the animation generation unit 212 creates an animation reflecting the estimation result and updates the display (step S205). For example, it is assumed that the value of the velocity is changed by the operation of the subject, and the values of the pitch and the vertical movement that change in conjunction with the change are estimated in the parameter estimation process. In this case, the animation generation unit 212 has the parameters on the left side of the screen shown in FIG. 5 so as to be the value of the velocity changed by the subject, the value of the pitch estimated by the parameter estimation process, and the value of the vertical movement. It changes the value and the position of the slide bar, creates an animation based on each of these values, and updates the animation displayed on the right side.

After the display update in step S205 is completed, or when the operation of changing the parameter is not accepted from the subject (step S203; No), the animation generation unit 212 generates an animation from the subject via the input unit 232. It is determined whether or not the instruction to end the process (for example, clicking the "end" button on the screen shown in FIG. 5) is accepted (step S206). If the end instruction is not received (step S206; No), the process returns to step S203. On the other hand, when the end instruction is received (step S206; Yes), the animation generation process ends.

As described above, according to the present embodiment, one parameter (for example, velocity) is selected from the set of parameters (for example, the set of velocity and pitch) indicating the exercise state of a plurality of subjects stored in the exercise state storage DB 222. ) Is input and the other parameter (for example, pitch) is output as a model (return line). Then, based on the generated model, it is estimated how the value of the other parameter changes when the value of the acquired parameter is changed. That is, according to the present embodiment, it is possible to estimate how the values of the other parameters change when one of the plurality of parameters indicating the exercise state changes or is assumed to change. It becomes.

Further, according to the present embodiment, when the value of one of the plurality of parameters indicating the exercise state is changed by the operation of the subject or the like, how the values of the other parameters change in conjunction with this. It is estimated whether to do it, and an animation showing the motion state is created based on the estimated parameter values. Therefore, even if only the value of one parameter changes, it is possible to create a natural animation.

Further, in the present embodiment, as a model for estimating the parameters, the reliability interval can be further obtained in addition to the regression line, and the parameters can be estimated in consideration of the length of the reliability interval. Therefore, it is possible to improve the estimation accuracy of the parameters.

(Modification example)
It should be noted that the present invention is not limited to the above embodiment, and various modifications can be made without departing from the gist of the present invention.

For example, in the above embodiment, in the parameter estimation process, a model is created from all the motion parameter information stored in the motion state storage DB 222, but the motion state of the subject having the same attributes as the subject to be animated. A model may be created from the motion parameter information corresponding to. For example, when the parameter indicating the exercise state of the subject who is a woman is estimated by the parameter estimation process, the parameter estimation unit 213 refers to the user DB 221 and performs the exercise parameter information corresponding to the exercise state of the woman from the exercise state storage DB 222. May be extracted and a model may be created from the extracted motion parameter information.

In the above embodiment, the velocity, pitch, and vertical movement of the subject are shown as examples of parameters representing the motion states that change in conjunction with each other, but the parameters are not limited to this, and other parameters are the first. It may be a parameter or a second parameter. For example, speed, pitch, vertical movement, stride, stride height ratio, vertical movement height ratio, left / right movement, forward / backward movement, contact time, swing time, contact time rate, deceleration amount, sinking amount, sinking amount height ratio. , Brake time, landing impact, kicking acceleration, kicking time, pelvic rotation amount, stiffness, stiffness weight ratio, ground contact angle, kicking angle It may be a parameter or a second parameter. It should be noted that these parameters can be calculated from the motion data acquired by the data transmission device 100 by a known method as well as the velocity, pitch, and vertical motion.

For example, the stride is the stride per step, and the stride can be obtained by dividing the speed per minute by the pitch. The stride height ratio can be determined by dividing the stride by the height of the subject. The vertical movement height ratio can be obtained by dividing the vertical movement by the height of the subject.

The left-right movement is the left-right fluctuation range of the position from the landing of one foot to the landing of the other foot, and the left-right movement can be calculated by integrating the left-right component of the acceleration indicated by the motion data. The anteroposterior movement is the range of variation in the anteroposterior direction of the position between the landing of one foot and the landing of the other foot. The back and forth movement can be calculated by subtracting.

The contact time is the time from when one foot touches the ground until the foot takes off, and the touchdown time is calculated by specifying the timing of touchdown and takeoff based on the acceleration indicated by the motion data. be able to. The swing time is the time from when one foot takes off to when that foot lands. The ground contact time rate can be obtained by the ground contact time / (ground contact time + swing time).

The deceleration amount can be obtained by integrating the magnitude of the acceleration vector in the receding direction in the ground contact section for one cycle of one foot based on the acceleration indicated by the motion data. The amount of subduction is the difference between the position of one foot at the time of landing and the lowest point thereafter, and can be obtained by integrating the vertical component of the acceleration indicated by the motion data from the time of landing to the lowest point. .. The subduction amount height ratio can be obtained by dividing the subduction amount by the height of the subject.

The braking time is the time from the time of touchdown until the anteroposterior component of acceleration changes in the propulsion direction, and specifies the timing of contact and the timing when the anteroposterior component of acceleration indicated by motion data changes in the propulsion direction. Can be obtained by. The landing impact is the amount of impact when touching the ground, and can be expressed by the magnitude of each component immediately after touching the ground in the acceleration vector indicated by the motion data.

The kicking acceleration is the magnitude of the acceleration during propulsion, and can be represented by the magnitude of the anteroposterior component of the acceleration vector indicated by the motion data. The kicking time is the time during which the acceleration in the propulsion direction is generated during the ground contact period, and can be obtained by measuring the time during which the anteroposterior component of the acceleration indicated by the motion data is generated. Alternatively, the kicking time may be obtained by measuring the time from the lowest point to the takeoff of one foot based on the vertical component of the acceleration indicated by the motion data.

The amount of pelvic rotation is the amount of rotation of the waist from the landing of one foot to the landing of the foot (two-step cycle), or from the landing of one foot to the landing of the other foot (one-step cycle). It can be obtained based on the rotational speed indicated by the motion data. Stiffness is a spring constant when the foot is regarded as a spring, and can be obtained based on the change in the vertical component of acceleration indicated by the motion data. The stiffness weight ratio can be determined by dividing the stiffness by the body weight of the subject.

The ground contact angle is the angle between the velocity vector at the time of touchdown and the horizontal plane or the ground, and the kicking angle is the angle between the velocity vector at the time of taking off and the horizontal plane or the ground. The ground contact angle and kicking angle can be calculated based on the components of the acceleration in each direction indicated by the motion data.

In the above embodiment, in the parameter estimation process, the values of the first parameter are input to the model which is the created regression equation to derive the first reference value and the second reference value, but the first reference value and the second reference value are derived from the model. The method for deriving the reference value is not limited to this. For example, a value obtained by multiplying the value of the first parameter by a coefficient may be input to the model to derive the first reference value and the second reference value.

In the above embodiment, the animation generation device 200 for creating an animation representing the running motion state of the subject has been described, but the motion state is not limited to running. For example, the present invention can be applied to an animation generator or the like that creates an animation of a baseball pitching form.

In the above embodiment, the animation generation device 200 for creating an animation representing the motion state of a human subject has been described as an example, but the target of the animation to be created is not limited to the human, and the subject other than the human is used. The present invention is also applicable to the animation generator 200 that creates an animation representing the motion state of the above. For example, the present invention can be applied to an animation generation device that generates an animation representing a running state of a racehorse, an operating state of a robot, and the like.

The present invention is not limited to the animation generator 200. For example, the present invention can be applied to an information processing apparatus or the like that executes only parameter estimation processing without creating an animation.

In the above embodiment, in the parameter estimation process, the animation generator 200 generated a model for estimating the parameters. However, a model may be generated in advance by an external server or the like, and in the parameter estimation process, the animation generation device 200 may estimate the parameters based on the model acquired from the external server or the like. By doing so, since the process of generating the model in the animation generation device 200 can be omitted, the load on the animation generation device 200 can be reduced, and the processing time of the parameter estimation process can be shortened.

Each function of the animation generation device 200 can also be performed by a computer such as a normal PC. Specifically, in the above embodiment, the animation generation processing program performed by the animation generation device 200 has been described as being stored in the ROM of the storage unit 220 in advance. However, the program can be a flexible disk, a CD-ROM (Compact Disc Read Only Memory), a DVD (Digital Versaille Disc), an MO (Magnet-Optical disc), a memory card, a USB (Universal Serial Bus) memory, or the like. A computer capable of realizing each of the above-mentioned functions may be configured by storing and distributing the program in a recording medium, reading the program into a computer, and installing the program.

Although the preferred embodiment of the present invention has been described above, the present invention is not limited to the specific embodiment, and the present invention includes the invention described in the claims and the equivalent range thereof. included. The inventions described in the original claims of the present application are described below.

(Appendix 1)
An acquisition means for acquiring the value of the first parameter and the value of the second parameter, which is an index different from the first parameter and having a correlation, as an index indicating the exercise state of a certain subject.
A parameter acquisition means for acquiring another first parameter, which is the first parameter having a value different from the value of the first parameter acquired by the acquisition means, and a parameter acquisition means.
Based on the set of the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter, which represent the motion state of each of the plurality of subjects of the same type as the certain subject. According to the model generated by inputting the value of the third parameter and outputting the value of the fourth parameter, the first reference value as the second parameter is derived based on the first parameter acquired by the acquisition means. The first derivation means to be
A second derivation means for deriving a second reference value as the second parameter based on the other first parameter acquired by the parameter acquisition means according to the model.
A parameter estimation means that estimates the value of the second parameter corresponding to the other first parameter based on the value of the second parameter, the first reference value, and the second reference value acquired by the acquisition means. When,
Information processing device equipped with.

(Appendix 2)
Animation generation that generates an animation showing the motion state of a certain subject based on the value of the other first parameter acquired by the parameter acquisition means and the value of the second parameter estimated by the parameter estimation means. Equipped with more means,
The information processing apparatus according to Appendix 1.

(Appendix 3)
The fourth parameter includes a certain ratio or more of all the sets of the value of the third parameter and the value of the fourth parameter representing the exercise state of each of the plurality of subjects. It also contains a confidence interval that indicates the range of values for,
In the parameter estimation means, the length of the reliability interval when the value of the third parameter is the value of the first parameter acquired by the acquisition means and the value of the third parameter are the values of the parameter acquisition means. The value of the second parameter is estimated based on the ratio of the length of the reliability interval when it is the acquired value of the other first parameter.
The information processing apparatus according to Appendix 1 or 2.

(Appendix 4)
The model is generated based on a set of a value of the third parameter and a value of the fourth parameter representing the kinetic state of each of a plurality of subjects of the same type and having the same attributes as the subject.
The information processing apparatus according to any one of Supplementary note 1 to 3.

(Appendix 5)
The first parameter and the second parameter are indexes related to the locomotion of a certain subject.
Each of the first parameter and the second parameter is the speed, pitch, vertical movement, stride, stride height ratio, vertical movement height ratio, left-right movement, back-and-forth movement, contact time, swing time, and contact time, respectively. Rate, deceleration amount, sinking amount, sinking amount height ratio, braking time, landing impact, kicking acceleration, kicking time, pelvic rotation amount, stiffness, stiffness weight ratio, ground contact angle, kicking angle. ,
The information processing apparatus according to any one of Supplementary note 1 to 4.

(Appendix 6)
An acquisition step for acquiring the value of the first parameter and the value of the second parameter, which is an index different from the first parameter and having a correlation, as an index representing the exercise state of a certain subject.
A parameter acquisition step for acquiring another first parameter which is the first parameter having a value different from the value of the first parameter acquired in the acquisition step, and
Based on the set of the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter, which represent the motion state of each of the plurality of subjects of the same type as the certain subject. According to the model generated by inputting the value of the third parameter and outputting the value of the fourth parameter, the first reference value as the second parameter is derived based on the first parameter acquired in the acquisition step. First derivation step and
A second derivation step for deriving a second reference value as the second parameter based on the other first parameter acquired in the parameter acquisition step according to the model.
A parameter estimation step for estimating the value of the second parameter corresponding to the other first parameter based on the value of the second parameter, the first reference value, and the second reference value acquired in the acquisition step. When,
Information processing method with.

(Appendix 7)
Computer,
An acquisition means for acquiring the value of the first parameter and the value of the second parameter, which is an index different from the first parameter and having a correlation, as an index indicating the exercise state of a certain subject.
A parameter acquisition means for acquiring another first parameter, which is the first parameter having a value different from the value of the first parameter acquired by the acquisition means.
Based on the set of the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter, which represent the motion state of each of the plurality of subjects of the same type as the certain subject. According to the model generated by inputting the value of the third parameter and outputting the value of the fourth parameter, the first reference value as the second parameter is derived based on the first parameter acquired by the acquisition means. First derivation means,
A second derivation means for deriving a second reference value as the second parameter based on the other first parameter acquired by the parameter acquisition means according to the model.
A parameter estimation means that estimates the value of the second parameter corresponding to the other first parameter based on the value of the second parameter, the first reference value, and the second reference value acquired by the acquisition means. ,
A program that functions as.

100 ... data transmission device, 110, 210 ... control unit, 111 ... motion data transmission unit, 120, 220 ... storage unit, 131, 231 ... communication unit, 132, 232 ... input unit, 133, 233 ... output unit, 134 ... Sensor unit, 200 ... animation generation device, 211 ... parameter acquisition unit, 212 ... animation generation unit, 213 ... parameter estimation unit, 221 ... user DB, 222 ... motion state storage DB, 1000 ... animation generation system, BL ... bus line

Claims (7)

An acquisition means for acquiring the value of the first parameter and the value of the second parameter, which is an index different from the first parameter and having a correlation, as an index indicating the exercise state of a certain subject.
A parameter acquisition means for acquiring another first parameter, which is the first parameter having a value different from the value of the first parameter acquired by the acquisition means, and a parameter acquisition means.
Based on the set of the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter, which represent the motion state of each of the plurality of subjects of the same type as the certain subject. According to the model generated by inputting the value of the third parameter and outputting the value of the fourth parameter, the first reference value as the second parameter is derived based on the first parameter acquired by the acquisition means. The first derivation means to be
A second derivation means for deriving a second reference value as the second parameter based on the other first parameter acquired by the parameter acquisition means according to the model.
A parameter estimation means that estimates the value of the second parameter corresponding to the other first parameter based on the value of the second parameter, the first reference value, and the second reference value acquired by the acquisition means. When,
Information processing device equipped with. Animation generation that generates an animation showing the motion state of a certain subject based on the value of the other first parameter acquired by the parameter acquisition means and the value of the second parameter estimated by the parameter estimation means. Equipped with more means,
The information processing apparatus according to claim 1. The fourth parameter includes a certain ratio or more of all the sets of the value of the third parameter and the value of the fourth parameter representing the exercise state of each of the plurality of subjects. It also contains a confidence interval that indicates the range of values for,
In the parameter estimation means, the length of the reliability interval when the value of the third parameter is the value of the first parameter acquired by the acquisition means and the value of the third parameter are the values of the parameter acquisition means. The value of the second parameter is estimated based on the ratio of the length of the reliability interval when it is the acquired value of the other first parameter.
The information processing apparatus according to claim 1 or 2. The model is generated based on a set of a value of the third parameter and a value of the fourth parameter representing the kinetic state of each of a plurality of subjects of the same type and having the same attributes as the subject.
The information processing apparatus according to any one of claims 1 to 3. The first parameter and the second parameter are indexes related to the locomotion of a certain subject.
Each of the first parameter and the second parameter is the speed, pitch, vertical movement, stride, stride height ratio, vertical movement height ratio, left-right movement, back-and-forth movement, contact time, swing time, and contact time, respectively. Rate, deceleration amount, sinking amount, sinking amount height ratio, braking time, landing impact, kicking acceleration, kicking time, pelvic rotation amount, stiffness, stiffness weight ratio, ground contact angle, kicking angle. ,
The information processing apparatus according to any one of claims 1 to 4. An acquisition step for acquiring the value of the first parameter and the value of the second parameter, which is an index different from the first parameter and having a correlation, as an index representing the exercise state of a certain subject.
A parameter acquisition step for acquiring another first parameter which is the first parameter having a value different from the value of the first parameter acquired in the acquisition step, and
Based on the set of the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter, which represent the motion state of each of the plurality of subjects of the same type as the certain subject. According to the model generated by inputting the value of the third parameter and outputting the value of the fourth parameter, the first reference value as the second parameter is derived based on the first parameter acquired in the acquisition step. First derivation step and
A second derivation step for deriving a second reference value as the second parameter based on the other first parameter acquired in the parameter acquisition step according to the model.
A parameter estimation step for estimating the value of the second parameter corresponding to the other first parameter based on the value of the second parameter, the first reference value, and the second reference value acquired in the acquisition step. When,
Information processing method with. Computer,
An acquisition means for acquiring the value of the first parameter and the value of the second parameter, which is an index different from the first parameter and having a correlation, as an index indicating the exercise state of a certain subject.
A parameter acquisition means for acquiring another first parameter, which is the first parameter having a value different from the value of the first parameter acquired by the acquisition means.
Based on the set of the value of the third parameter of the same type as the first parameter and the value of the fourth parameter of the same type as the second parameter, which represent the motion state of each of the plurality of subjects of the same type as the certain subject. According to the model generated by inputting the value of the third parameter and outputting the value of the fourth parameter, the first reference value as the second parameter is derived based on the first parameter acquired by the acquisition means. First derivation means,
A second derivation means for deriving a second reference value as the second parameter based on the other first parameter acquired by the parameter acquisition means according to the model.
A parameter estimation means that estimates the value of the second parameter corresponding to the other first parameter based on the value of the second parameter, the first reference value, and the second reference value acquired by the acquisition means. ,
A program that functions as.

Images